INDEX

Explanations

export statements in a programming context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

wis

-0.15

uk

-0.15

untime

-0.14

avanaugh

-0.14

lop

-0.14

 Smarty

-0.14

YP

-0.14

 barg

-0.14

Smarty

-0.14

cast

-0.14

POSITIVE LOGITS

 default

0.30

 const

0.29

 function

0.29

default

0.23

 interface

0.23

-default

0.23

.ar

0.21

 enum

0.21

function

0.20

 defaults

0.20

Activations Density 0.003%

export statements in a programming context

No Comments

No Known Activations